# Assessing the Sufficiency of Arguments through Conclusion Generation

arXiv: https://arxiv.org/abs/2110.13495 · HTML: https://mlsanity.com/paper/2110.13495/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 26 Oct 2021.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Parsing Argumentation Structures in Persuasive Essays](https://mlsanity.com/paper/1604.07370/) (2016)
- [A Large-scale Dataset for Argument Quality Ranking: Construction and Analysis](https://mlsanity.com/paper/1911.11408/) (2019)
- [Automatic Argument Quality Assessment -- New Datasets and Methods](https://mlsanity.com/paper/1909.01007/) (2019)
- [Scalable Learning of Non-Decomposable Objectives](https://mlsanity.com/paper/1608.04802/) (2016)
- [Rhetoric, Logic, and Dialectic: Advancing Theory-based Argument Quality Assessment in Natural Language Processing](https://mlsanity.com/paper/2006.00843/) (2020)
- [Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale](https://mlsanity.com/paper/2101.10250/) (2021)
- [Generating Informative Conclusions for Argumentative Texts](https://mlsanity.com/paper/2106.01064/) (2021)
- [Intrinsic Quality Assessment of Arguments](https://mlsanity.com/paper/2010.12473/) (2020)

## Built on by (most cited first, 11 of 11)

- [Large Language Models in Argument Mining: A Survey](https://mlsanity.com/paper/2506.16383/) (2025)
- [Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation](https://mlsanity.com/paper/2406.03151/) (2024)
- [Architectural Sweet Spots for Modeling Human Label Variation by the Example of Argument Quality: It's Best to Relate Perspectives!](https://mlsanity.com/paper/2311.03153/) (2023)
- [A School Student Essay Corpus for Analyzing Interactions of Argumentative Structure and Quality](https://mlsanity.com/paper/2404.02529/) (2024)
- [Contextualizing Argument Quality Assessment with Relevant Knowledge](https://mlsanity.com/paper/2305.12280/) (2023)
- [CASA: Causality-driven Argument Sufficiency Assessment](https://mlsanity.com/paper/2401.05249/) (2024)
- [Argument Quality Assessment in the Age of Instruction-Following Large Language Models](https://mlsanity.com/paper/2403.16084/) (2024)
- [Claim Optimization in Computational Argumentation](https://mlsanity.com/paper/2212.08913/) (2022)
- [Conclusion-based Counter-Argument Generation](https://mlsanity.com/paper/2301.09911/) (2023)
- [Debating for Better Reasoning: An Unsupervised Multimodal Approach](https://mlsanity.com/paper/2505.14627/) (2025)
- [GRASP: Deterministic argument ranking in interaction graphs](https://mlsanity.com/paper/2605.19141/) (2026)

## Abstract (arXiv)

The premises of an argument give evidence or other reasons to support a conclusion. However, the amount of support required depends on the generality of a conclusion, the nature of the individual premises, and similar. An argument whose premises make its conclusion rationally worthy to be drawn is called sufficient in argument quality research. Previous work tackled sufficiency assessment as a standard text classification problem, not modeling the inherent relation of premises and conclusion. In this paper, we hypothesize that the conclusion of a sufficient argument can be generated from its premises. To study this hypothesis, we explore the potential of assessing sufficiency based on the output of large-scale pre-trained language models. Our best model variant achieves an F1-score of .885, outperforming the previous state-of-the-art and being on par with human experts. While manual evaluation reveals the quality of the generated conclusions, their impact remains low ultimately.